Abstract: Designing new molecules is essential for drug discovery and material science. Recently, deep generative models that aim to model molecule distribution have made promising progress in ...

In this work, our proposed method takes an underwater-captured image as input and outputs a restored image, free from the effects of the water medium, along with a depth estimation of the scene.

While 3D content generation has advanced significantly, existing methods still face challenges with input formats, latent space design, and output representations. This paper introduces a novel 3D ...

Abstract: The advancement of fingerprint research within public academic circles has been trailing behind facial recognition, primarily due to the scarcity of extensive publicly available datasets, ...